OneHot#

class bayesflow.adapters.transforms.OneHot(num_classes: int)[source]#

Bases: ElementwiseTransform

Changes data to be one-hot encoded.

Parameters:

num_classesint: Number of classes for the encoding.

get_config() → dict[source]#

forward(data: ndarray, **kwargs) → ndarray[source]#

inverse(data: ndarray, **kwargs) → ndarray[source]#

__call__(data: ndarray, inverse: bool = False, **kwargs) → ndarray#: Call self as a function.

classmethod from_config(config: dict, custom_objects=None)#